Clustering Transactions Based on Weighting Maximal Frequent Itemsets

摘要：

We propose a new similarity measure forcomparing maximal frequent itemset(MFI),whichtakes into account not only non-numeric attributes butalso numeric attributes of each item while computingsimilarity between MFIs.This provides more reliablesoundness for clustering results interpretation.Traditional approaches consider just one side and areapt to lead to unintelligible clustering results fordecision-makers.Based on properties of maximalfrequent itemset(MFI),we construct a multi-levelhierarchical model(MHM)for our clusteringalgorithm.Moreover,to evaluate our approach andcompare with other similarity strategies,we constructan original evaluating strategy NF_Measure whichintegrates both quantity similarity and qualifysimilarity between transactions.We experimentallyevaluate the proposed approach and demonstrate thatour algorithm is promising and effective.

作者: Faliang Huang Guoqing Xie Zhiqiang Yao Shengzhen Cai

作者单位: Faculty of Software,Fujian Normal University,Fuzhou 350007,China;School of Computer Science and Engineering South China University of Technology,Guangzhou,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 262-266

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）